Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2607 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4414. Min Range: -4.4414
Max Act: 4.4414. Min Act: -0.1700
Data Index: 6496403 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4414. Min Range: -4.4414
Max Act: 4.3476. Min Act: -0.1700
Data Index: 1997801 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4414. Min Range: -4.4414
Max Act: 4.2851. Min Act: -0.1700
Data Index: 2127692 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4414. Min Range: -4.4414
Max Act: 4.2851. Min Act: -0.1698
Data Index: 962353 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4414. Min Range: -4.4414
Max Act: 4.2851. Min Act: -0.1700
Data Index: 738527 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4414. Min Range: -4.4414
Max Act: 4.2851. Min Act: -0.1700
Data Index: 5219230 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4414. Min Range: -4.4414
Max Act: 4.2851. Min Act: -0.1700
Data Index: 1609072 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4414. Min Range: -4.4414
Max Act: 4.2851. Min Act: -0.1699
Data Index: 299388 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4414. Min Range: -4.4414
Max Act: 4.2851. Min Act: -0.1700
Data Index: 893079 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4414. Min Range: -4.4414
Max Act: 4.2851. Min Act: -0.1700
Data Index: 7704279 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4414. Min Range: -4.4414
Max Act: 4.2851. Min Act: -0.1700
Data Index: 8630504 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4414. Min Range: -4.4414
Max Act: 4.2851. Min Act: -0.1700
Data Index: 5646366 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4414. Min Range: -4.4414
Max Act: 4.2539. Min Act: -0.1700
Data Index: 4935569 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4414. Min Range: -4.4414
Max Act: 4.2539. Min Act: -0.1700
Data Index: 7391963 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4414. Min Range: -4.4414
Max Act: 4.2539. Min Act: -0.1700
Data Index: 6428919 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4414. Min Range: -4.4414
Max Act: 4.2851. Min Act: -0.1700
Data Index: 5997998 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4414. Min Range: -4.4414
Max Act: 4.2539. Min Act: -0.1700
Data Index: 5105357 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4414. Min Range: -4.4414
Max Act: 4.2539. Min Act: -0.1700
Data Index: 1250266 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4414. Min Range: -4.4414
Max Act: 4.2539. Min Act: -0.1700
Data Index: 1572302 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4414. Min Range: -4.4414
Max Act: 4.2539. Min Act: -0.1700
Data Index: 1828328 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19